{"uid":"cap_5JFNU4jHamjgDyRwPyP-x","slug":"modelprices-xyz-gpt-pricing-table-d8a31e5e","name":"modelprices.xyz GPT Pricing Table","description":"GPT pricing table: what every GPT model costs per token right now — GPT-5, GPT-5 mini, GPT-4o, GPT-4.1, o3 — from OpenAI and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare GPT inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.","url":"https://modelprices.xyz/gpt-pricing","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","properties":{}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_deuX1a72pVtzX68_1qoTG","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Returns current per-token pricing for all GPT models (GPT-5, GPT-4o, GPT-4.1, o3, etc.) across every host that serves them — OpenAI, Azure, Bedrock, Vertex, OpenRouter, Fireworks — sorted cheapest first.","exampleAgentPrompt":"Pull the latest GPT pricing table from modelprices.xyz — I need input, output, cache, and batch costs per million tokens for every GPT model across OpenAI, Azure, Bedrock, Vertex, OpenRouter, and Fireworks, sorted cheapest first so I can pick the most cost-effective host.","exampleUseCases":[{"title":"Cheapest GPT-4o host selection","prompt":"I'm about to deploy a high-volume app using GPT-4o — can you check modelprices.xyz right now and tell me which provider (OpenAI, Azure, Bedrock, Vertex, OpenRouter, Fireworks) currently has the lowest input and output token prices for it?"},{"title":"Budget planning for GPT inference","prompt":"I need to estimate monthly costs for running around 50 million tokens a day through a GPT-4.1 model — can you grab the current pricing table for all GPT models across every host and show me the cheapest options for both input and output tokens?"},{"title":"Comparing batch vs real-time GPT pricing","prompt":"What's the difference in price between batch and real-time inference for GPT-5 mini right now? Pull the full GPT pricing table and highlight where batch rates give meaningful savings."}],"resultDescription":"A normalized pricing table listing every GPT model variant (GPT-5, GPT-5 mini, GPT-4o, GPT-4.1, o3, etc.) available across all major hosts, with columns for input, output, cache, and batch prices in USD per 1M tokens, sorted ascending by cost. Data is refreshed hourly and cross-checked across providers.","failureModes":["Pricing data may be temporarily stale if upstream provider APIs are unavailable during hourly refresh","Provider may not list all GPT variants if a host has not published pricing (row omitted)","Payment failure (402) if USDC payment of $0.01 is not properly attached","Network timeout if modelprices.xyz is temporarily unreachable"],"whenToPreferThis":"Use this endpoint when you need a cross-provider GPT pricing comparison in a single call — specifically when you want to compare OpenAI, Azure, AWS Bedrock, Google Vertex, OpenRouter, and Fireworks side-by-side for GPT-family models. Prefer this over scraping individual provider pricing pages, or over sibling endpoints on modelprices.xyz that cover other model families (Claude, Bedrock-all, DeepInfra, etc.).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:43:29.653Z","isFirstParty":false}